C++ PageLocked函数代码示例

//.........这里部分代码省略.........
		update_inode_page(old_inode);
		update_inode_page(new_inode);
	} else {
		err = f2fs_add_link(new_dentry, old_inode);
		if (err)
			goto out_dir;

		if (old_dir_entry) {
			inc_nlink(new_dir);
			update_inode_page(new_dir);
		}
	}

	old_inode->i_ctime = CURRENT_TIME;
	mark_inode_dirty(old_inode);

	f2fs_delete_entry(old_entry, old_page, NULL);

	if (old_dir_entry) {
		if (old_dir != new_dir) {
			f2fs_set_link(old_inode, old_dir_entry,
						old_dir_page, new_dir);
			F2FS_I(old_inode)->i_pino = new_dir->i_ino;
			update_inode_page(old_inode);
		} else {
			kunmap(old_dir_page);
			f2fs_put_page(old_dir_page, 0);
		}
		drop_nlink(old_dir);
		mark_inode_dirty(old_dir);
		update_inode_page(old_dir);
	}

	f2fs_unlock_op(sbi);
	return 0;

put_out_dir:
	if (PageLocked(new_page))
		f2fs_put_page(new_page, 1);
	else
		f2fs_put_page(new_page, 0);
out_dir:
	if (old_dir_entry) {
		kunmap(old_dir_page);
		f2fs_put_page(old_dir_page, 0);
	}
	f2fs_unlock_op(sbi);
out_old:
	kunmap(old_page);
	f2fs_put_page(old_page, 0);
out:
	return err;
}

const struct inode_operations f2fs_dir_inode_operations = {
	.create		= f2fs_create,
	.lookup		= f2fs_lookup,
	.link		= f2fs_link,
	.unlink		= f2fs_unlink,
	.symlink	= f2fs_symlink,
	.mkdir		= f2fs_mkdir,
	.rmdir		= f2fs_rmdir,
	.mknod		= f2fs_mknod,
	.rename		= f2fs_rename,
	.getattr	= f2fs_getattr,
	.setattr	= f2fs_setattr,
	.get_acl	= f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= f2fs_listxattr,
	.removexattr	= generic_removexattr,
#endif
};

const struct inode_operations f2fs_symlink_inode_operations = {
	.readlink       = generic_readlink,
	.follow_link    = page_follow_link_light,
	.put_link       = page_put_link,
	.getattr	= f2fs_getattr,
	.setattr	= f2fs_setattr,
#ifdef CONFIG_F2FS_FS_XATTR
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= f2fs_listxattr,
	.removexattr	= generic_removexattr,
#endif
};

const struct inode_operations f2fs_special_inode_operations = {
	.getattr	= f2fs_getattr,
	.setattr        = f2fs_setattr,
	.get_acl	= f2fs_get_acl,
#ifdef CONFIG_F2FS_FS_XATTR
	.setxattr       = generic_setxattr,
	.getxattr       = generic_getxattr,
	.listxattr	= f2fs_listxattr,
	.removexattr    = generic_removexattr,
#endif
};

static void __free_pages_ok (struct page *page, unsigned int order)
{
	unsigned long index, page_idx, mask, flags;
	free_area_t *area;
	struct page *base;
	zone_t *zone;

	/*
	 * Yes, think what happens when other parts of the kernel take 
	 * a reference to a page in order to pin it for io. -ben
	 */
	if (PageLRU(page)) {
		if (unlikely(in_interrupt()))
			BUG();
		lru_cache_del(page);
	}

	if (page->buffers)
		BUG();
	if (page->mapping)
		BUG();
	if (!VALID_PAGE(page))
		BUG();
	if (PageLocked(page))
		BUG();
	if (PageActive(page))
		BUG();
	page->flags &= ~((1<<PG_referenced) | (1<<PG_dirty));

	if (current->flags & PF_FREE_PAGES)
		goto local_freelist;
 back_local_freelist:

	zone = page_zone(page);

	mask = (~0UL) << order;
	base = zone->zone_mem_map;
	page_idx = page - base;
	if (page_idx & ~mask)
		BUG();
	index = page_idx >> (1 + order);

	area = zone->free_area + order;

	spin_lock_irqsave(&zone->lock, flags);

	zone->free_pages -= mask;

	while (mask + (1 << (MAX_ORDER-1))) {
		struct page *buddy1, *buddy2;

		if (area >= zone->free_area + MAX_ORDER)
			BUG();
		if (!__test_and_change_bit(index, area->map))
			/*
			 * the buddy page is still allocated.
			 */
			break;
		/*
		 * Move the buddy up one level.
		 * This code is taking advantage of the identity:
		 * 	-mask = 1+~mask
		 */
		buddy1 = base + (page_idx ^ -mask);
		buddy2 = base + page_idx;
		if (BAD_RANGE(zone,buddy1))
			BUG();
		if (BAD_RANGE(zone,buddy2))
			BUG();

		list_del(&buddy1->list);
		mask <<= 1;
		area++;
		index >>= 1;
		page_idx &= mask;
	}
	list_add(&(base + page_idx)->list, &area->free_list);

	spin_unlock_irqrestore(&zone->lock, flags);
	return;

 local_freelist:
	if (current->nr_local_pages)
		goto back_local_freelist;
	if (in_interrupt())
		goto back_local_freelist;		

	list_add(&page->list, &current->local_pages);
	page->index = order;
	current->nr_local_pages++;
}

/*
 * AFS read page from file, directory or symlink
 */
static int afs_readpage(struct file *file, struct page *page)
{
	struct afs_vnode *vnode;
	struct inode *inode;
	struct key *key;
	size_t len;
	off_t offset;
	int ret;

	inode = page->mapping->host;

	if (file) {
		key = file->private_data;
		ASSERT(key != NULL);
	} else {
		key = afs_request_key(AFS_FS_S(inode->i_sb)->volume->cell);
		if (IS_ERR(key)) {
			ret = PTR_ERR(key);
			goto error_nokey;
		}
	}

	_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);

	vnode = AFS_FS_I(inode);

	BUG_ON(!PageLocked(page));

	ret = -ESTALE;
	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
		goto error;

	/* is it cached? */
#ifdef CONFIG_AFS_FSCACHE
	ret = fscache_read_or_alloc_page(vnode->cache,
					 page,
					 afs_file_readpage_read_complete,
					 NULL,
					 GFP_KERNEL);
#else
	ret = -ENOBUFS;
#endif
	switch (ret) {
		/* read BIO submitted (page in cache) */
	case 0:
		break;

		/* page not yet cached */
	case -ENODATA:
		_debug("cache said ENODATA");
		goto go_on;

		/* page will not be cached */
	case -ENOBUFS:
		_debug("cache said ENOBUFS");
	default:
	go_on:
		offset = page->index << PAGE_CACHE_SHIFT;
		len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);

		/* read the contents of the file from the server into the
		 * page */
		ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
		if (ret < 0) {
			if (ret == -ENOENT) {
				_debug("got NOENT from server"
				       " - marking file deleted and stale");
				set_bit(AFS_VNODE_DELETED, &vnode->flags);
				ret = -ESTALE;
			}

#ifdef CONFIG_AFS_FSCACHE
			fscache_uncache_page(vnode->cache, page);
#endif
			BUG_ON(PageFsCache(page));
			goto error;
		}

		SetPageUptodate(page);

		/* send the page to the cache */
#ifdef CONFIG_AFS_FSCACHE
		if (PageFsCache(page) &&
		    fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
			fscache_uncache_page(vnode->cache, page);
			BUG_ON(PageFsCache(page));
		}
#endif
		unlock_page(page);
	}

	if (!file)
		key_put(key);
	_leave(" = 0");
	return 0;

error:
//.........这里部分代码省略.........

int jffs2_do_readpage_nolock (struct inode *inode, struct page *pg)
{
	struct jffs2_inode_info *f = JFFS2_INODE_INFO(inode);
	struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb);
	struct jffs2_node_frag *frag = f->fraglist;
	__u32 offset = pg->index << PAGE_CACHE_SHIFT;
	__u32 end = offset + PAGE_CACHE_SIZE;
	unsigned char *pg_buf;
	int ret;

	D1(printk(KERN_DEBUG "jffs2_do_readpage_nolock(): ino #%lu, page at offset 0x%x\n", inode->i_ino, offset));

	if (!PageLocked(pg))
                PAGE_BUG(pg);

	while(frag && frag->ofs + frag->size  <= offset) {
		//		D1(printk(KERN_DEBUG "skipping frag %d-%d; before the region we care about\n", frag->ofs, frag->ofs + frag->size));
		frag = frag->next;
	}

	pg_buf = kmap(pg);

	/* XXX FIXME: Where a single physical node actually shows up in two
	   frags, we read it twice. Don't do that. */
	/* Now we're pointing at the first frag which overlaps our page */
	while(offset < end) {
		D2(printk(KERN_DEBUG "jffs2_readpage: offset %d, end %d\n", offset, end));
		if (!frag || frag->ofs > offset) {
			__u32 holesize = end - offset;
			if (frag) {
				D1(printk(KERN_NOTICE "Eep. Hole in ino %ld fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n", inode->i_ino, frag->ofs, offset));
				holesize = min(holesize, frag->ofs - offset);
				D1(jffs2_print_frag_list(f));
			}
			D1(printk(KERN_DEBUG "Filling non-frag hole from %d-%d\n", offset, offset+holesize));
			memset(pg_buf, 0, holesize);
			pg_buf += holesize;
			offset += holesize;
			continue;
		} else if (frag->ofs < offset && (offset & (PAGE_CACHE_SIZE-1)) != 0) {
			D1(printk(KERN_NOTICE "Eep. Overlap in ino #%ld fraglist. frag->ofs = 0x%08x, offset = 0x%08x\n",
				  inode->i_ino, frag->ofs, offset));
			D1(jffs2_print_frag_list(f));
			memset(pg_buf, 0, end - offset);
			ClearPageUptodate(pg);
			SetPageError(pg);
			kunmap(pg);
			return -EIO;
		} else if (!frag->node) {
			__u32 holeend = min(end, frag->ofs + frag->size);
			D1(printk(KERN_DEBUG "Filling frag hole from %d-%d (frag 0x%x 0x%x)\n", offset, holeend, frag->ofs, frag->ofs + frag->size));
			memset(pg_buf, 0, holeend - offset);
			pg_buf += holeend - offset;
			offset = holeend;
			frag = frag->next;
			continue;
		} else {
			__u32 readlen;
			__u32 fragofs; /* offset within the frag to start reading */

			fragofs = offset - frag->ofs;
			readlen = min(frag->size - fragofs, end - offset);
			D1(printk(KERN_DEBUG "Reading %d-%d from node at 0x%x\n", frag->ofs+fragofs, 
				  fragofs+frag->ofs+readlen, frag->node->raw->flash_offset & ~3));
			ret = jffs2_read_dnode(c, frag->node, pg_buf, fragofs + frag->ofs - frag->node->ofs, readlen);
			D2(printk(KERN_DEBUG "node read done\n"));
			if (ret) {
				D1(printk(KERN_DEBUG"jffs2_readpage error %d\n",ret));
				memset(pg_buf, 0, readlen);
				ClearPageUptodate(pg);
				SetPageError(pg);
				kunmap(pg);
				return ret;
			}
		
			pg_buf += readlen;
			offset += readlen;
			frag = frag->next;
			D2(printk(KERN_DEBUG "node read was OK. Looping\n"));
		}
	}
	D2(printk(KERN_DEBUG "readpage finishing\n"));
	SetPageUptodate(pg);
	ClearPageError(pg);

	flush_dcache_page(pg);

	kunmap(pg);
	D1(printk(KERN_DEBUG "readpage finished\n"));
	return 0;
}

int lock_kiovec(int nr, struct kiobuf *iovec[], int wait)
{
	struct kiobuf *iobuf;
	int i, j;
	struct page *page, **ppage;
	int doublepage = 0;
	int repeat = 0;
	
 repeat:
	
	for (i = 0; i < nr; i++) {
		iobuf = iovec[i];

		if (iobuf->locked)
			continue;
		iobuf->locked = 1;

		ppage = iobuf->maplist;
		for (j = 0; j < iobuf->nr_pages; ppage++, j++) {
			page = *ppage;
			if (!page)
				continue;
			
			if (TryLockPage(page))
				goto retry;
		}
	}

	return 0;
	
 retry:
	
	/* 
	 * We couldn't lock one of the pages.  Undo the locking so far,
	 * wait on the page we got to, and try again.  
	 */
	
	unlock_kiovec(nr, iovec);
	if (!wait)
		return -EAGAIN;
	
	/* 
	 * Did the release also unlock the page we got stuck on?
	 */
	if (!PageLocked(page)) {
		/* 
		 * If so, we may well have the page mapped twice
		 * in the IO address range.  Bad news.  Of
		 * course, it _might_ just be a coincidence,
		 * but if it happens more than once, chances
		 * are we have a double-mapped page. 
		 */
		if (++doublepage >= 3) 
			return -EINVAL;
		
		/* Try again...  */
		wait_on_page(page);
	}
	
	if (++repeat < 16)
		goto repeat;
	return -EAGAIN;
}

/*
 * AFS read page from file, directory or symlink
 */
static int afs_readpage(struct file *file, struct page *page)
{
	struct afs_vnode *vnode;
	struct inode *inode;
	struct key *key;
	size_t len;
	off_t offset;
	int ret;

	inode = page->mapping->host;

	ASSERT(file != NULL);
	key = file->private_data;
	ASSERT(key != NULL);

	_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);

	vnode = AFS_FS_I(inode);

	BUG_ON(!PageLocked(page));

	ret = -ESTALE;
	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
		goto error;

#ifdef AFS_CACHING_SUPPORT
	/* is it cached? */
	ret = cachefs_read_or_alloc_page(vnode->cache,
					 page,
					 afs_file_readpage_read_complete,
					 NULL,
					 GFP_KERNEL);
#else
	ret = -ENOBUFS;
#endif

	switch (ret) {
		/* read BIO submitted and wb-journal entry found */
	case 1:
		BUG(); // TODO - handle wb-journal match

		/* read BIO submitted (page in cache) */
	case 0:
		break;

		/* no page available in cache */
	case -ENOBUFS:
	case -ENODATA:
	default:
		offset = page->index << PAGE_CACHE_SHIFT;
		len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);

		/* read the contents of the file from the server into the
		 * page */
		ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
		if (ret < 0) {
			if (ret == -ENOENT) {
				_debug("got NOENT from server"
				       " - marking file deleted and stale");
				set_bit(AFS_VNODE_DELETED, &vnode->flags);
				ret = -ESTALE;
			}
#ifdef AFS_CACHING_SUPPORT
			cachefs_uncache_page(vnode->cache, page);
#endif
			goto error;
		}

		SetPageUptodate(page);

#ifdef AFS_CACHING_SUPPORT
		if (cachefs_write_page(vnode->cache,
				       page,
				       afs_file_readpage_write_complete,
				       NULL,
				       GFP_KERNEL) != 0
		    ) {
			cachefs_uncache_page(vnode->cache, page);
			unlock_page(page);
		}
#else
		unlock_page(page);
#endif
	}

	_leave(" = 0");
	return 0;

error:
	SetPageError(page);
	unlock_page(page);
	_leave(" = %d", ret);
	return ret;
}

/* Sharing code of page_mkwrite method for rhel5 and rhel6 */
static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
			    bool *retry)
{
	struct lu_env	   *env;
	struct cl_io	    *io;
	struct vvp_io	   *vio;
	struct cl_env_nest       nest;
	int		      result;
	sigset_t	     set;
	struct inode	     *inode;
	struct ll_inode_info     *lli;

	io = ll_fault_io_init(vma, &env,  &nest, vmpage->index, NULL);
	if (IS_ERR(io)) {
		result = PTR_ERR(io);
		goto out;
	}

	result = io->ci_result;
	if (result < 0)
		goto out_io;

	io->u.ci_fault.ft_mkwrite = 1;
	io->u.ci_fault.ft_writable = 1;

	vio = vvp_env_io(env);
	vio->u.fault.ft_vma    = vma;
	vio->u.fault.ft_vmpage = vmpage;

	set = cfs_block_sigsinv(sigmask(SIGKILL) | sigmask(SIGTERM));

	/* we grab lli_trunc_sem to exclude truncate case.
	 * Otherwise, we could add dirty pages into osc cache
	 * while truncate is on-going.
	 */
	inode = ccc_object_inode(io->ci_obj);
	lli = ll_i2info(inode);
	down_read(&lli->lli_trunc_sem);

	result = cl_io_loop(env, io);

	up_read(&lli->lli_trunc_sem);

	cfs_restore_sigs(set);

	if (result == 0) {
		struct inode *inode = file_inode(vma->vm_file);
		struct ll_inode_info *lli = ll_i2info(inode);

		lock_page(vmpage);
		if (!vmpage->mapping) {
			unlock_page(vmpage);

			/* page was truncated and lock was cancelled, return
			 * ENODATA so that VM_FAULT_NOPAGE will be returned
			 * to handle_mm_fault().
			 */
			if (result == 0)
				result = -ENODATA;
		} else if (!PageDirty(vmpage)) {
			/* race, the page has been cleaned by ptlrpcd after
			 * it was unlocked, it has to be added into dirty
			 * cache again otherwise this soon-to-dirty page won't
			 * consume any grants, even worse if this page is being
			 * transferred because it will break RPC checksum.
			 */
			unlock_page(vmpage);

			CDEBUG(D_MMAP, "Race on page_mkwrite %p/%lu, page has been written out, retry.\n",
			       vmpage, vmpage->index);

			*retry = true;
			result = -EAGAIN;
		}

		if (result == 0) {
			spin_lock(&lli->lli_lock);
			lli->lli_flags |= LLIF_DATA_MODIFIED;
			spin_unlock(&lli->lli_lock);
		}
	}

out_io:
	cl_io_fini(env, io);
	cl_env_nested_put(&nest, env);
out:
	CDEBUG(D_MMAP, "%s mkwrite with %d\n", current->comm, result);
	LASSERT(ergo(result == 0, PageLocked(vmpage)));

	return result;
}

static void page_cache_tree_delete(struct address_space *mapping,
				   struct page *page, void *shadow)
{
	struct radix_tree_node *node;
	unsigned long index;
	unsigned int offset;
	unsigned int tag;
	void **slot;

	VM_BUG_ON(!PageLocked(page));

	__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot);

	if (shadow) {
		mapping->nrshadows++;
		/*
		 * Make sure the nrshadows update is committed before
		 * the nrpages update so that final truncate racing
		 * with reclaim does not see both counters 0 at the
		 * same time and miss a shadow entry.
		 */
		smp_wmb();
	}
	mapping->nrpages--;

	if (!node) {
		/* Clear direct pointer tags in root node */
		mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;
		radix_tree_replace_slot(slot, shadow);
		return;
	}

	/* Clear tree tags for the removed page */
	index = page->index;
	offset = index & RADIX_TREE_MAP_MASK;
	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
		if (test_bit(offset, node->tags[tag]))
			radix_tree_tag_clear(&mapping->page_tree, index, tag);
	}

	/* Delete page, swap shadow entry */
	radix_tree_replace_slot(slot, shadow);
	workingset_node_pages_dec(node);
	if (shadow)
		workingset_node_shadows_inc(node);
	else
		if (__radix_tree_delete_node(&mapping->page_tree, node))
			return;

	/*
	 * Track node that only contains shadow entries.
	 *
	 * Avoid acquiring the list_lru lock if already tracked.  The
	 * list_empty() test is safe as node->private_list is
	 * protected by mapping->tree_lock.
	 */
	if (!workingset_node_pages(node) &&
	    list_empty(&node->private_list)) {
		node->private_data = mapping;
		list_lru_add(&workingset_shadow_nodes, &node->private_list);
	}
}

/* Sharing code of page_mkwrite method for rhel5 and rhel6 */
static int ll_page_mkwrite0(struct vm_area_struct *vma, struct page *vmpage,
                            bool *retry)
{
	struct lu_env           *env;
	struct cl_io            *io;
	struct vvp_io           *vio;
	int                      result;
	__u16			 refcheck;
	sigset_t		 set;
	struct inode             *inode;
	struct ll_inode_info     *lli;
	ENTRY;

	LASSERT(vmpage != NULL);
	env = cl_env_get(&refcheck);
	if (IS_ERR(env))
		RETURN(PTR_ERR(env));

	io = ll_fault_io_init(env, vma, vmpage->index, NULL);
	if (IS_ERR(io))
		GOTO(out, result = PTR_ERR(io));

	result = io->ci_result;
	if (result < 0)
		GOTO(out_io, result);

	io->u.ci_fault.ft_mkwrite = 1;
	io->u.ci_fault.ft_writable = 1;

	vio = vvp_env_io(env);
	vio->u.fault.ft_vma    = vma;
	vio->u.fault.ft_vmpage = vmpage;

	set = cfs_block_sigsinv(sigmask(SIGKILL) | sigmask(SIGTERM));

	inode = vvp_object_inode(io->ci_obj);
	lli = ll_i2info(inode);

	result = cl_io_loop(env, io);

	cfs_restore_sigs(set);

        if (result == 0) {
                lock_page(vmpage);
                if (vmpage->mapping == NULL) {
                        unlock_page(vmpage);

                        /* page was truncated and lock was cancelled, return
                         * ENODATA so that VM_FAULT_NOPAGE will be returned
                         * to handle_mm_fault(). */
                        if (result == 0)
                                result = -ENODATA;
                } else if (!PageDirty(vmpage)) {
                        /* race, the page has been cleaned by ptlrpcd after
                         * it was unlocked, it has to be added into dirty
                         * cache again otherwise this soon-to-dirty page won't
                         * consume any grants, even worse if this page is being
                         * transferred because it will break RPC checksum.
                         */
                        unlock_page(vmpage);

                        CDEBUG(D_MMAP, "Race on page_mkwrite %p/%lu, page has "
                               "been written out, retry.\n",
                               vmpage, vmpage->index);

                        *retry = true;
                        result = -EAGAIN;
                }

		if (result == 0)
			ll_file_set_flag(lli, LLIF_DATA_MODIFIED);
        }
        EXIT;

out_io:
	cl_io_fini(env, io);
out:
	cl_env_put(env, &refcheck);
	CDEBUG(D_MMAP, "%s mkwrite with %d\n", current->comm, result);
	LASSERT(ergo(result == 0, PageLocked(vmpage)));

	return result;
}

int ext4_bio_write_page(struct ext4_io_submit *io,
			struct page *page,
			int len,
			struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	struct ext4_io_page *io_page;
	struct buffer_head *bh, *head;
	int ret = 0;

	blocksize = 1 << inode->i_blkbits;

	BUG_ON(!PageLocked(page));
	BUG_ON(PageWriteback(page));

	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
	if (!io_page) {
		set_page_dirty(page);
		unlock_page(page);
		return -ENOMEM;
	}
	io_page->p_page = page;
	atomic_set(&io_page->p_count, 1);
	get_page(page);
	set_page_writeback(page);
	ClearPageError(page);

	for (bh = head = page_buffers(page), block_start = 0;
	     bh != head || !block_start;
	     block_start = block_end, bh = bh->b_this_page) {

		block_end = block_start + blocksize;
		if (block_start >= len) {
			/*
			 * Comments copied from block_write_full_page_endio:
			 *
			 * The page straddles i_size.  It must be zeroed out on
			 * each and every writepage invocation because it may
			 * be mmapped.  "A file is mapped in multiples of the
			 * page size.  For a file that is not a multiple of
			 * the  page size, the remaining memory is zeroed when
			 * mapped, and writes to that region are not written
			 * out to the file."
			 */
			zero_user_segment(page, block_start, block_end);
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
			continue;
		}
		clear_buffer_dirty(bh);
		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
		if (ret) {
			set_page_dirty(page);
			break;
		}
	}
	unlock_page(page);
	put_io_page(io_page);
	return ret;
}

void bd_put_page(struct page *page)
{
    if(PageLocked(page))
        unlock_page(page);
    page_cache_release(page);
}

/*
* "Get" data from cleancache associated with the poolid/inode/index
* that were specified when the data was put to cleanache and, if
* successful, use it to fill the specified page with data and return 0.
* The pageframe is unchanged and returns -1 if the get fails.
* Page must be locked by caller.
*/
int __cleancache_get_page(struct page *page)
{
int ret = -1;
int pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };

VM_BUG_ON(!PageLocked(page));
pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (pool_id < 0)
goto out;

if (cleancache_get_key(page->mapping->host, &key) < 0)
goto out;

ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page);
if (ret == 0)
cleancache_succ_gets++;
else
cleancache_failed_gets++;
out:
return ret;
}
EXPORT_SYMBOL(__cleancache_get_page);

/*
* "Put" data from a page to cleancache and associate it with the
* (previously-obtained per-filesystem) poolid and the page's,
* inode and page index. Page must be locked. Note that a put_page
* always "succeeds", though a subsequent get_page may succeed or fail.
*/
void __cleancache_put_page(struct page *page)
{
int pool_id;
struct cleancache_filekey key = { .u.key = { 0 } };

VM_BUG_ON(!PageLocked(page));
pool_id = page->mapping->host->i_sb->cleancache_poolid;
if (pool_id >= 0 &&
cleancache_get_key(page->mapping->host, &key) >= 0) {
(*cleancache_ops.put_page)(pool_id, key, page->index, page);
cleancache_puts++;
}
}
EXPORT_SYMBOL(__cleancache_put_page);

/*
* Flush any data from cleancache associated with the poolid and the
* page's inode and page index so that a subsequent "get" will fail.
*/
void __cleancache_flush_page(struct address_space *mapping, struct page *page)
{
/* careful... page->mapping is NULL sometimes when this is called */
int pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };

if (pool_id >= 0) {
VM_BUG_ON(!PageLocked(page));
if (cleancache_get_key(mapping->host, &key) >= 0) {
(*cleancache_ops.flush_page)(pool_id, key, page->index);
cleancache_flushes++;
}
}
}
EXPORT_SYMBOL(__cleancache_flush_page);

/*
* Flush all data from cleancache associated with the poolid and the
* mappings's inode so that all subsequent gets to this poolid/inode
* will fail.
*/
void __cleancache_flush_inode(struct address_space *mapping)
{
int pool_id = mapping->host->i_sb->cleancache_poolid;
struct cleancache_filekey key = { .u.key = { 0 } };

if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
(*cleancache_ops.flush_inode)(pool_id, key);
}
EXPORT_SYMBOL(__cleancache_flush_inode);

/*
* Called by any cleancache-enabled filesystem at time of unmount;
* note that pool_id is surrendered and may be reutrned by a subsequent
* cleancache_init_fs or cleancache_init_shared_fs
*/
void __cleancache_flush_fs(struct super_block *sb)
{
if (sb->cleancache_poolid >= 0) {
int old_poolid = sb->cleancache_poolid;
sb->cleancache_poolid = -1;
(*cleancache_ops.flush_fs)(old_poolid);
}
}
//.........这里部分代码省略.........

int ext4_bio_write_page(struct ext4_io_submit *io,
			struct page *page,
			int len,
			struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	struct ext4_io_page *io_page;
	struct buffer_head *bh, *head;
	int ret = 0;

	blocksize = 1 << inode->i_blkbits;

	BUG_ON(!PageLocked(page));
	BUG_ON(PageWriteback(page));

	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
	if (!io_page) {
		set_page_dirty(page);
		unlock_page(page);
		return -ENOMEM;
	}
	io_page->p_page = page;
	atomic_set(&io_page->p_count, 1);
	get_page(page);
	set_page_writeback(page);
	ClearPageError(page);

	for (bh = head = page_buffers(page), block_start = 0;
	     bh != head || !block_start;
	     block_start = block_end, bh = bh->b_this_page) {

		block_end = block_start + blocksize;
		if (block_start >= len) {
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
			continue;
		}
		clear_buffer_dirty(bh);
		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
		if (ret) {
			/*
			 * We only get here on ENOMEM.  Not much else
			 * we can do but mark the page as dirty, and
			 * better luck next time.
			 */
			set_page_dirty(page);
			break;
		}
	}
	unlock_page(page);
	/*
	 * If the page was truncated before we could do the writeback,
	 * or we had a memory allocation error while trying to write
	 * the first buffer head, we won't have submitted any pages for
	 * I/O.  In that case we need to make sure we've cleared the
	 * PageWriteback bit from the page to prevent the system from
	 * wedging later on.
	 */
	put_io_page(io_page);
	return ret;
}

/*
 * "Get" data from cleancache associated with the poolid/inode/index
 * that were specified when the data was put to cleanache and, if
 * successful, use it to fill the specified page with data and return 0.
 * The pageframe is unchanged and returns -1 if the get fails.
 * Page must be locked by caller.
 */
int __cleancache_get_page(struct page *page)
{
	int ret = -1;
	int pool_id;
	struct cleancache_filekey key = { .u.key = { 0 } };

	VM_BUG_ON(!PageLocked(page));
	pool_id = page->mapping->host->i_sb->cleancache_poolid;
	if (pool_id < 0)
		goto out;

	if (cleancache_get_key(page->mapping->host, &key) < 0)
		goto out;

	ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page);
	if (ret == 0)
		cleancache_succ_gets++;
	else
		cleancache_failed_gets++;
out:
	return ret;
}
EXPORT_SYMBOL(__cleancache_get_page);

/*
 * "Put" data from a page to cleancache and associate it with the
 * (previously-obtained per-filesystem) poolid and the page's,
 * inode and page index.  Page must be locked.  Note that a put_page
 * always "succeeds", though a subsequent get_page may succeed or fail.
 */
void __cleancache_put_page(struct page *page)
{
	int pool_id;
	struct cleancache_filekey key = { .u.key = { 0 } };

	VM_BUG_ON(!PageLocked(page));
	pool_id = page->mapping->host->i_sb->cleancache_poolid;
	if (pool_id >= 0 &&
	      cleancache_get_key(page->mapping->host, &key) >= 0) {
		(*cleancache_ops.put_page)(pool_id, key, page->index, page);
		cleancache_puts++;
	}
}
EXPORT_SYMBOL(__cleancache_put_page);

/*
 * Invalidate any data from cleancache associated with the poolid and the
 * page's inode and page index so that a subsequent "get" will fail.
 */
void __cleancache_invalidate_page(struct address_space *mapping,
					struct page *page)
{
	/* careful... page->mapping is NULL sometimes when this is called */
	int pool_id = mapping->host->i_sb->cleancache_poolid;
	struct cleancache_filekey key = { .u.key = { 0 } };

	if (pool_id >= 0) {
		VM_BUG_ON(!PageLocked(page));
		if (cleancache_get_key(mapping->host, &key) >= 0) {
			(*cleancache_ops.invalidate_page)(pool_id,
							  key, page->index);
			cleancache_invalidates++;
		}
	}
}
EXPORT_SYMBOL(__cleancache_invalidate_page);

/*
 * Invalidate all data from cleancache associated with the poolid and the
 * mappings's inode so that all subsequent gets to this poolid/inode
 * will fail.
 */
void __cleancache_invalidate_inode(struct address_space *mapping)
{
	int pool_id = mapping->host->i_sb->cleancache_poolid;
	struct cleancache_filekey key = { .u.key = { 0 } };

	if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
		(*cleancache_ops.invalidate_inode)(pool_id, key);
}
EXPORT_SYMBOL(__cleancache_invalidate_inode);

/*
 * Called by any cleancache-enabled filesystem at time of unmount;
 * note that pool_id is surrendered and may be reutrned by a subsequent
 * cleancache_init_fs or cleancache_init_shared_fs
 */
void __cleancache_invalidate_fs(struct super_block *sb)
{
	if (sb->cleancache_poolid >= 0) {
		int old_poolid = sb->cleancache_poolid;
		sb->cleancache_poolid = -1;
		(*cleancache_ops.invalidate_fs)(old_poolid);
//.........这里部分代码省略.........

int ext4_bio_write_page(struct ext4_io_submit *io,
			struct page *page,
			int len,
			struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	unsigned block_start, block_end, blocksize;
	struct ext4_io_page *io_page;
	struct buffer_head *bh, *head;
	int ret = 0;

	blocksize = 1 << inode->i_blkbits;

	BUG_ON(!PageLocked(page));
	BUG_ON(PageWriteback(page));

	io_page = kmem_cache_alloc(io_page_cachep, GFP_NOFS);
	if (!io_page) {
		set_page_dirty(page);
		unlock_page(page);
		return -ENOMEM;
	}
	io_page->p_page = page;
	atomic_set(&io_page->p_count, 1);
	get_page(page);
	set_page_writeback(page);
	ClearPageError(page);

	/*
	 * Comments copied from block_write_full_page_endio:
	 *
	 * The page straddles i_size.  It must be zeroed out on each and every
	 * writepage invocation because it may be mmapped.  "A file is mapped
	 * in multiples of the page size.  For a file that is not a multiple of
	 * the page size, the remaining memory is zeroed when mapped, and
	 * writes to that region are not written out to the file."
	 */
	if (len < PAGE_CACHE_SIZE)
		zero_user_segment(page, len, PAGE_CACHE_SIZE);

	for (bh = head = page_buffers(page), block_start = 0;
	     bh != head || !block_start;
	     block_start = block_end, bh = bh->b_this_page) {

		block_end = block_start + blocksize;
		if (block_start >= len) {
			clear_buffer_dirty(bh);
			set_buffer_uptodate(bh);
			continue;
		}
		clear_buffer_dirty(bh);
		ret = io_submit_add_bh(io, io_page, inode, wbc, bh);
		if (ret) {
			/*
			 * We only get here on ENOMEM.  Not much else
			 * we can do but mark the page as dirty, and
			 * better luck next time.
			 */
			set_page_dirty(page);
			break;
		}
	}
	unlock_page(page);
	/*
	 * If the page was truncated before we could do the writeback,
	 * or we had a memory allocation error while trying to write
	 * the first buffer head, we won't have submitted any pages for
	 * I/O.  In that case we need to make sure we've cleared the
	 * PageWriteback bit from the page to prevent the system from
	 * wedging later on.
	 */
	put_io_page(io_page);
	return ret;
}